New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Decision Journal

by itseffi in itseffi/agentic-os

Create structured records of decisions with expected outcomes, probabilities, and quit conditions.

MITAuto-check passed

Install Decision Journal

skills CLI
$ npx skills add itseffi/agentic-os --skill decision-journal -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install itseffi/agentic-os decision-journal --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/itseffi/agentic-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/decision-journal .claude/skills/decision-journal && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
decision-journal
GitHub stars
115
Token cost
~396 tokens
SKILL.md length
197 words
Files
2
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Create structured records of decisions with expected outcomes, probabilities, and quit conditions.

  • Works in 6 steps: Expected Outcomes → Probability Estimates → Key Assumptions → …
  • Important decisions
  • SKILL.md covers When to Use, The Framework, Review Process and When Not to Use
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Decision Journal is an agent skill from itseffi/agentic-os. Create structured records of decisions with expected outcomes, probabilities, and quit conditions. Use for important decisions.

Its SKILL.md is about 400 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms. The licence is MIT.

When your agent uses it

  • Important decisions

Example prompts

  • “/decision-journal”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Expected Outcomes
  2. Probability Estimates
  3. Key Assumptions
  4. Base Rates
  5. Quit Conditions
  6. Actual Results

What it can do on your machine

Read from SKILL.md and the folder at commit e54d0ac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Decision Journal loads about 396 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 197 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~396

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from itseffi/agentic-os at commit e54d0ac, republished under its MIT licence (© itseffi). 197 words, ~396 tokens.

Download SKILL.mdSave it as .claude/skills/decision-journal/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
decision-journal
description
Create structured records of decisions with expected outcomes, probabilities, and quit conditions. Use for important decisions.

Decision Journal

Create structured records of decisions for learning and accountability.

When to Use

When making important decisions that you want to track and learn from.

The Framework

Record these components for each decision:

1. Expected Outcomes

List 3-5 possible outcomes:

  • Best case scenario
  • Most likely scenario
  • Worst case scenario
  • Consider short and long-term
2. Probability Estimates

For each outcome, estimate likelihood (must sum to 100%):

  • Outcome A: X%
  • Outcome B: Y%
  • etc.
3. Key Assumptions

List 3-5 critical assumptions:

  • What beliefs underlie this decision?
  • Which, if wrong, would change the outcome?
4. Base Rates

Research relevant statistics:

  • What's typical for this type of decision?
  • Historical data or industry averages?
  • What do similar situations suggest?
5. Quit Conditions

Define 2-3 triggers to abandon or change course:

  • Clear, measurable indicators
  • Specific thresholds
  • Timeline checkpoints
6. Actual Results

Leave blank initially, fill in later:

  • What actually happened?
  • Which outcome occurred?
  • Were assumptions valid?

Review Process

After outcomes are known:

  1. Compare predictions to reality
  2. Identify where thinking was wrong
  3. Extract lessons for future decisions

When Not to Use

Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

© itseffi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/decision-journal of itseffi/agentic-os.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit e54d0ac

Compare with similar skills

Decision Journal next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Decision Journal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decision Journal this skillitseffi/agentic-os115—~396Automated safety check: PassMIT
Recordingcodewhale-hq/Codewhale41k—~540Automated safety check: PassMIT
Architecture Decision Recordsaffaan-m/ECC275k4 repos~1.8kAutomated safety check: PassMIT
Architecture Decision Recordsaffaan-m/ECC275k1 repos~863Automated safety check: PassMIT
Architecture Decision Recordsaffaan-m/ECC275k—~1.1kAutomated safety check: PassMIT
Browser Recordruvnet/ruflo74k—~735Automated safety check: NotesMIT

Similar skills

  • Recording

    codewhale-hq/Codewhale

    Capture screenshots on registered computers, record on macOS or HarmonyOS, and manage saved captures.

    41k GitHub stars~540 tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Architecture Decision Records

    affaan-m/ECC

    Capture architectural decisions as numbered ADR markdown files in docs/adr/ with context, alternatives considered, consequences, and an index README.

    275k GitHub starsUsed in 4 repos~1.8k tokens
    DevelopmentAuto-check passed

  • Architecture Decision Records

    affaan-m/ECC

    在Claude Code会话期间，将做出的架构决策捕获为结构化的架构决策记录（ADR）。自动检测决策时刻，记录上下文、考虑的替代方案和理由。维护一个ADR日志，以便未来的开发人员理解代码库为何以当前方式构建。

    275k GitHub starsUsed in 1 repo~863 tokens
    DevelopmentAuto-check passed

  • Architecture Decision Records

    affaan-m/ECC

    コーディングセッション中にアーキテクチャ決定を構造化ADRとして記録し、自動的に決定の瞬間を検出し、コンテキスト、検討された代替案、根拠を記録します。今後の開発者がコードベースの形成理由を理解するためのADRログを維持します。

    275k GitHub stars~1.1k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Browser Record

    ruvnet/ruflo

    Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action

    74k GitHub stars~735 tokensUpdated today
    Agent WorkflowsAuto-check: notes

  • Grill And Record

    asgeirtj/system_prompts_leaks

    Run an explicitly requested decision interview and record each settled decision in durable project documentation.

    69k GitHub stars~912 tokensUpdated today
    Auto-check passed

More from itseffi/agentic-os

All 29 skills in this repo

  • Atlassian Jira Sync

    itseffi/agentic-os

    Sync Jira issues with local tasks. An agent skill from itseffi/agentic-os.

    115 GitHub stars~515 tokensUpdated yesterday
    Auto-check passed

  • Davci

    itseffi/agentic-os

    Define clear decision rights - Decider, Approver, Veto, Consulted, Informed.

    115 GitHub stars~563 tokensUpdated yesterday
    Auto-check passed

  • Google Calendar Schedule Check

    itseffi/agentic-os

    Check Google Calendar for today's schedule. An agent skill from itseffi/agentic-os.

    115 GitHub stars~467 tokensUpdated yesterday
    Auto-check passed

  • Granola Meeting Sync

    itseffi/agentic-os

    Sync new Granola meetings to local Knowledge folder. An agent skill from itseffi/agentic-os.

    115 GitHub stars~535 tokensUpdated yesterday
    Auto-check passed

  • Linear Issue Sync

    itseffi/agentic-os

    Sync Linear issues with local tasks. An agent skill from itseffi/agentic-os.

    115 GitHub stars~468 tokensUpdated yesterday
    Auto-check passed

  • Slack Message Check

    itseffi/agentic-os

    Check Slack for important messages and activity. An agent skill from itseffi/agentic-os.

    115 GitHub stars~465 tokensUpdated yesterday
    Auto-check passed

Questions about Decision Journal

What does Decision Journal do?

Create structured records of decisions with expected outcomes, probabilities, and quit conditions. Decision Journal is an agent skill from itseffi/agentic-os. Create structured records of decisions with expected outcomes, probabilities, and quit conditions.

When should I use Decision Journal?

Decision Journal fits situations like: important decisions.

How do I install Decision Journal in Claude Code?

Run `npx skills add itseffi/agentic-os --skill decision-journal -a claude-code`. Or copy the skill folder (.agents/skills/decision-journal in itseffi/agentic-os) into .claude/skills/decision-journal in your project. Claude Code loads it when a task matches its description.

How do I install Decision Journal in Codex?

Run `npx skills add itseffi/agentic-os --skill decision-journal -a codex`. Or copy the skill folder (.agents/skills/decision-journal in itseffi/agentic-os) into .agents/skills/decision-journal in your project. Codex loads it when a task matches its description.

Can I use Decision Journal in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add itseffi/agentic-os --skill decision-journal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/decision-journal, .gemini/skills/decision-journal, .github/skills/decision-journal and .opencode/skills/decision-journal in your project.

What does Decision Journal need to run?

SKILL.md names no scripts, command-line tools or credentials: Decision Journal is instructions for the agent only.

Does Decision Journal access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Decision Journal safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Decision Journal use?

Decision Journal is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Decision Journal use?

About 396 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Decision Journal?

Skills that share tags, products or a category with Decision Journal: Recording (codewhale-hq/Codewhale, 41k stars), Architecture Decision Records (affaan-m/ECC, 275k stars), Architecture Decision Records (affaan-m/ECC, 275k stars) and Architecture Decision Records (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decision Journal?

itseffi (a GitHub user) maintains it in itseffi/agentic-os, which has 115 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 7, 2026.

Source: itseffi/agentic-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.